Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Nanocrystals Technology for Pharmaceutical Science.

Current pharmaceutical design·2018
Same author

PGC1α promotes cisplatin resistance in human ovarian carcinoma cells through upregulation of mitochondrial biogenesis.

International journal of oncology·2018
Same author

[Type and key drivers of nitrification for an acidic peat soil in Xiaoxing'an Mountain, China].

Ying yong sheng tai xue bao = The journal of applied ecology·2018
Same author

Initial brain metastasis velocity: does the rate at which cancers first seed the brain affect outcomes?

Journal of neuro-oncology·2018
Same author

Hsa_Circ_0001275: A Potential Novel Diagnostic Biomarker for Postmenopausal Osteoporosis.

Cellular physiology and biochemistry : international journal of experimental cellular physiology, biochemistry, and pharmacology·2018
Same author

G3BP1 promotes tumor progression and metastasis through IL-6/G3BP1/STAT3 signaling axis in renal cell carcinomas.

Cell death & disease·2018

Related Experiment Video

Updated: Dec 17, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.6K

Electroencephalogram classification in motor-imagery brain-computer interface applications based on double-constraint

Jing Su1, Zuyuan Yang1,2, Wei Yan1,3

  • 1School of Automation, Guangdong Key Laboratory of IoT Information Technology, Guangdong University of Technology, Guangzhou 510006, People's Republic of China.

Physiological Measurement
|June 27, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces double-constrained nonnegative matrix factorization (DCNMF) to enhance motor imagery (MI) brain-computer interface (BCI) performance. The novel DCNMF method significantly improves classification accuracy for MI EEG signals.

More Related Videos

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.9K
Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.5K

Related Experiment Videos

Last Updated: Dec 17, 2025

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality
10:14

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

1.6K
Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients
09:42

Author Spotlight: Using Motor Imagery Brain-Computer Interface to Improve Motor and Cognitive Function in Stroke Patients

Published on: September 1, 2023

1.9K
Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.5K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Brain-computer interfaces (BCIs) aim to establish communication between the brain and external devices.
  • Motor imagery (MI) signal classification is crucial for BCI systems.
  • Electroencephalogram (EEG) signals used in MI BCIs are non-stationary with weak class properties, hindering performance.

Purpose of the Study:

  • To improve the classification performance of motor imagery (MI) signals in brain-computer interface (BCI) systems.
  • To address the limitations of unsupervised Nonnegative Matrix Factorization (NMF) by incorporating label information.
  • To introduce a novel method, double-constrained nonnegative matrix factorization (DCNMF), for enhanced MI BCI analysis.

Main Methods:

  • Proposed a novel double-constrained nonnegative matrix factorization (DCNMF) method for MI EEG data.
  • Constructed label matrices as constraints within the NMF procedure.
  • Ensured similar low-dimensional representations for same-class EEGs and dissimilar representations for different-class EEGs.

Main Results:

  • Achieved higher average accuracy on BCI competition III datasets (79.00% for dataset I, 77.78% for dataset IVa).
  • Demonstrated performance improvement of approximately 10% compared to existing literature.
  • Extracted features exhibited clear class properties, optimizing MI EEG classification.

Conclusions:

  • The DCNMF method offers a novel, label-constrained solution for MI BCI analysis.
  • Facilitates semi-supervised feature learning for improved BCI performance.
  • Significantly enhances the classification accuracy of motor imagery electroencephalogram signals.